
Software Engineer, Guardian
AI
OpenAI is hiring a Software Engineer for the Guardian team in London to build safety and oversight systems for AI agents. The role involves designing production systems that evaluate agent behavior, detect risk, and integrate with alignment research and product teams. Candidates should have strong software engineering fundamentals and experience with AI agents or large language models.
What you'll do
- Design, build, and operate core components of Auto-review and the broader Guardian platform, balancing safety, product utility, latency, and operational reliability.
- Build production systems that evaluate agent actions in real time, detect potentially harmful behavior, and support safe recovery or escalation paths.
- Improve how oversight systems understand user intent, environmental context, permissions, and relevant personalization signals while protecting privacy and avoiding unnecessary friction.
What you need
Must-have
AI agentsLarge Language ModelsBackend servicesAPIsInfrastructureSoftware engineering fundamentalsProduction softwareEvaluations
Soft skills
Product judgmentCommunicationInitiativeComfort with ambiguityCollaboration
Software EngineerAI safetyAI agentsLarge Language ModelsResearch ServicesLondonOn-siteFull-time